Forecasting and early warning of shield tunnelling-induced ground collapse in rock-soil interface mixed ground using multivariate data fusion and Catastrophe Theory

Engineering Geology, Journal Year: 2024, Volume and Issue: 335, P. 107548 - 107548

Published: May 10, 2024

Language: Английский

---

An improved population segmentation-based multi-mutation differential evolution algorithm for parameter extraction of photovoltaic models

Energy Conversion and Management, Journal Year: 2025, Volume and Issue: 327, P. 119553 - 119553

Published: Jan. 28, 2025

Language: Английский

---

Task-Driven Virtual Machine Optimization Placement Model and Algorithm

Future Internet, Journal Year: 2025, Volume and Issue: 17(2), P. 73 - 73

Published: Feb. 7, 2025

In cloud data centers, determining how to balance the interests of user and service provider is a challenging issue. this study, task-loading-oriented virtual machine (VM) optimization placement model algorithm proposed integrating consideration both VM user’s computing requirements. First, modeled as multi-objective problem minimize makespan loading tasks, rental costs, energy consumption centers; then, an improved chaos-elite NSGA-III (CE-NSGAIII) presented by casting logistic mapping-based population initialization (LMPI) elite-guided in NSGA-III; finally, CE-NSGAIII employed solve aforementioned model, further, through combination above sub-algorithms, CE-NSGAIII-based method developed. The experiment results show that Pareto solution set obtained using exhibits better convergence diversity than those compared algorithms yields optimized scheme with shorter makespan, less lower consumption.

Language: Английский

---

Improvement of differential evolution variants with nonlinear population adjustment and parameter adaption

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 126945 - 126945

Published: Feb. 1, 2025

Language: Английский

---

A periodic intervention and strategic collaboration mechanisms based differential evolution algorithm for global optimization

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 113137 - 113137

Published: April 1, 2025

Language: Английский

---

Rolling discrete grey periodic power model with interaction effect under dual processing and its application

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 254, P. 124487 - 124487

Published: June 13, 2024

Language: Английский

---

Multi-Objective Optimization of Resilient, Sustainable, and Safe Urban Bus Routes for Tourism Promotion Using a Hybrid Reinforcement Learning Algorithm

Mathematics, Journal Year: 2024, Volume and Issue: 12(14), P. 2283 - 2283

Published: July 22, 2024

Urban transportation systems in tourism-centric cities face challenges from rapid urbanization and population growth. Efficient, resilient, sustainable bus route optimization is essential to ensure reliable service, minimize environmental impact, maintain safety standards. This study presents a novel Hybrid Reinforcement Learning-Variable Neighborhood Strategy Adaptive Search (H-RL-VaNSAS) algorithm for multi-objective urban optimization. Our mathematical model maximizes resilience, sustainability, tourist satisfaction, accessibility while minimizing total travel distance. H-RL-VaNSAS evaluated against leading methods, including the Crested Porcupine Optimizer (CPO), Krill Herd Algorithm (KHA), Salp Swarm (SSA). Using metrics such as Hypervolume Average Ratio of Pareto Optimal Solutions, demonstrates superior performance. Specifically, achieved highest resilience index (550), sustainability (370), score (480), preferences (300), (2300), distance 950 km. Compared other improved by 12.24–17.02%, 5.71–12.12%, 4.35–9.09%, 7.14–13.21%, 4.55–9.52%, reduced 9.52–17.39%. research offers framework designing efficient, public transit that align with planning goals. The integration reinforcement learning VaNSAS significantly enhances capabilities, providing valuable tool communities.

Language: Английский

---

An improved reinforcement learning-based differential evolution algorithm for combined economic and emission dispatch problems

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 140, P. 109709 - 109709

Published: Nov. 29, 2024

Language: Английский

---

A novel binary genetic differential evolution optimization algorithm for wind layout problems

AIMS energy, Journal Year: 2024, Volume and Issue: 12(1), P. 321 - 349

Published: Jan. 1, 2024

<abstract><p>This paper addresses the increasingly critical issue of environmental optimization in context rapid economic development, with a focus on wind farm layout optimization. As demand for sustainable resource management, climate change mitigation, and biodiversity conservation rises, so does complexity managing impacts promoting practices. Wind optimization, vital subset involves strategic placement turbines to maximize energy production minimize impacts. Traditional methods, such as heuristic approaches, gradient-based rule-based strategies, have been employed tackle these challenges. However, they often face limitations exploring solution space efficiently avoiding local optima. To advance field, this study introduces LSHADE-SPAGA, novel algorithm that combines binary genetic operator LSHADE differential evolution algorithm, effectively balancing global exploration exploitation capabilities. This hybrid approach is designed navigate complexities considering factors like patterns, terrain, land use constraints. Extensive testing, including 156 instances across different scenarios constraints, demonstrates LSHADE-SPAGA's superiority over seven state-of-the-art algorithms both ability jumping out optima quality.</p></abstract>

Language: Английский

---

Differential Evolution for Classification: A Novel Classifier Technique in Data Mining

Published: Feb. 28, 2024

In the realm of Data Mining, pursuit innovative classification methodologies remains crucial for advancing robust techniques in handling complex and diverse datasets. This paper explores application Differential Evolution (DE), a powerful optimization algorithm, as unique effective optimization-based standalone classifier. Our exploration focused on harnessing DE's intrinsic capabilities, adapting it into classifier while preserving its distinctiveness. The fundamental principle DE involves iteratively optimizing center point each class using operators, which are specialized mechanisms exploring refining solutions, utilizing these optimized points making predictions. effectiveness our model was evaluated ten datasets from UCI Machine Learning Repository compared against three other methods: KNN, ZMP, BPNN. Experimental results underscore competitive performance proposed model, emphasizing potential effectively addressing challenges.

Language: Английский

---